adalbertojunior
/

Llama-3-8B-Instruct-Portuguese-v0.2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

adalbertojunior commited on Apr 22

Commit

12f8741

•

1 Parent(s): c874cc8

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ prompt = pipeline.tokenizer.apply_chat_template(
 terminators = [
     pipeline.tokenizer.eos_token_id,
-    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
 ]
 outputs = pipeline(

 terminators = [
     pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|im_end|>")
 ]
 outputs = pipeline(